Semantically Guided Efficient Attention Transformer for Face Super-Resolution Tasks

Cong Han, Youqiang Gui, Peng Cheng and Zhisheng You
Additional contact information
Cong Han: Sichuan University, China
Youqiang Gui: Sichuan University, China
Peng Cheng: Sichuan University, China
Zhisheng You: Sichuan University, China

International Journal on Semantic Web and Information Systems (IJSWIS), 2025, vol. 21, issue 1, 1-24

Abstract: Face super-resolution generates high-resolution face images from low-resolution inputs, supporting face recognition in challenging environments. While deep learning methods, like Stable Diffusion and origin Transformer-based framework, have advanced super-resolution, they require heavy computation, making them difficult for tasks like face recognition. However, recognition accuracy only needs images of size 112x112, reducing the necessity for extremely large outputs. Existing methods often rely on convolutional attention, limiting receptive fields and performance. To address this, we propose SETFSR, a Semantically Guided Efficient Attention Transformer Face Super-Resolution. Our model leverages efficient self-attention for global feature extraction and incorporates face parsing constraints for structural accuracy. Experiments on Helen, CelebA, and FFHQ datasets show that SETFSR outperforms state-of-the-art models in PSNR, SSIM, and identity preservation.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJSWIS.364097 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jswis0:v:21:y:2025:i:1:p:1-24

Access Statistics for this article

International Journal on Semantic Web and Information Systems (IJSWIS) is currently edited by Brij Gupta

More articles in International Journal on Semantic Web and Information Systems (IJSWIS) from IGI Global
Bibliographic data for series maintained by Journal Editor ().